Ilia Rushkin

Yigal Rosen, Ilia Rushkin

Generative AI is rapidly transforming how organizations create value and evaluate talent. While large language models enhance baseline output quality, they simultaneously introduce ambiguity in assessing human creativity, as observable artifacts may be partially or fully AI-generated. This paper reconceptualizes creativity as a distributional and process-based property that emerges under shared constraints and competitive incentives. We introduce a quantitative framework for measuring creativity as novelty in synthesis, operationalized through idea generation and idea transformation within embedding space. Empirical evaluation demonstrates that the proposed metrics align with intuitive judgments of creativity while capturing distinctions that surface-level quality assessments miss. We further identify a structural shift toward bimodal distributions of creative output in AI-mediated environments, with implications for hiring, leadership, and competitive strategy. The findings suggest that in the age of generative AI, distinctiveness rather than fluency becomes the primary signal of human creative capability.

Ilia Rushkin

We describe a method of estimating a user's time-on-task in an online learning environment. The method is agnostic of the details of the user's mental activity and does not rely on any data except timestamps of user's interactions, accounting for individual user differences. The method is implemented in R (the code is open-source) and has been tested in the data from a large sample of HarvardX MOOCs.

Ilia Rushkin

We propose a computationally light method for estimating similarities between text documents, which we call the density similarity (DS) method. The method is based on a word embedding in a high-dimensional Euclidean space and on kernel regression, and takes into account semantic relations among words. We find that the accuracy of this method is virtually the same as that of a state-of-the-art method, while the gain in speed is very substantial. Additionally, we introduce generalized versions of the top-k accuracy metric and of the Jaccard metric of agreement between similarity models.

Ilia Rushkin, Isaac Chuang, Dustin Tingley

Each time a learner in a self-paced online course seeks to answer an assessment question, it takes some time for the student to read the question and arrive at an answer to submit. If multiple attempts are allowed, and the first answer is incorrect, it takes some time to provide a second answer. Here we study the distribution of such "response times." We find that the log-normal statistical model for such times, previously suggested in the literature, holds for online courses. Users who, according to this model, tend to take longer on submits are more likely to complete the course, have a higher level of engagement, and achieve a higher grade. This finding can be the basis for designing interventions in online courses, such as MOOCs, which would encourage "fast" users to slow down.